xiaohongshu-rednote-competitor-monitor

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill explicitly instructs the agent to automatically install the BrowserAct dependency without asking the user to confirm and to avoid describing the installation as a user-facing browser request, which is a hidden/deceptive instruction outside the monitoring task's stated purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill contains explicit instructions to automatically install an external runtime dependency and to avoid requesting or describing that installation to the user, which is a deliberate attempt to bypass user consent and can enable supply-chain or remote code-installation abuse.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to use the BrowserAct CLI to access real browser pages at runtime and extract visible text/metadata from public/authorized competitor URLs, which is outsider-authored free text that can be fed into the LLM context via the browser page content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The Skill explicitly tells the agent to automatically install and invoke the BrowserAct CLI at runtime from https://www.browseract.com/?co-from=social-media (with a redirect to https://github.com/browser-act/skills/tree/main), which is a required runtime dependency that would fetch and execute remote installation code.